diff --git a/llvm/docs/CommandGuide/llvm-exegesis.rst b/llvm/docs/CommandGuide/llvm-exegesis.rst
--- a/llvm/docs/CommandGuide/llvm-exegesis.rst
+++ b/llvm/docs/CommandGuide/llvm-exegesis.rst
@@ -30,6 +30,20 @@
 :program:`llvm-exegesis` can also benchmark arbitrary user-provided code
 snippets.
 
+SUPPORTED PLATFORMS
+-------------------
+
+:program:`llvm-exegesis` currently only supports X86 (64-bit only), ARM(AArch64
+only), MIPS, and PowerPC on Linux. Not all functionality is guaranteed to work
+on every platform.
+
+SUPPORTED PLATFORMS
+-------------------
+
+:program:`llvm-exegesis` currently only supports X86 (64-bit only), ARM(AArch64
+only), MIPS, and PowerPC on Linux. Not all functionality is guaranteed to work
+on every platform.
+
 SNIPPET ANNOTATIONS
 -------------------
 
diff --git a/llvm/tools/llvm-exegesis/README.md b/llvm/tools/llvm-exegesis/README.md
new file mode 100644
--- /dev/null
+++ b/llvm/tools/llvm-exegesis/README.md
@@ -0,0 +1,32 @@
+# llvm-exegesis
+
+`llvm-exegesis` is a benchmarking tool that accepts or assembles a snippet and
+can measure characteristics of that snippet by executing it while keeping track
+of performance counters.
+
+### Currently Supported Platforms
+
+`llvm-exegesis` is quite platform-dependent and currently only supports a couple
+platform configurations.
+
+##### Currently Supported Operating Systems
+
+Currently, `llvm-exegesis` only supports Linux. This is mainly due to a
+dependency on the Linux perf subsystem for reading performance counters.
+In addition, `llvm-exegesis` currently only implements the System V
+calling convention internally (used to pass data from the executing process
+to the snippet), further limiting platform independence.
+
+##### Currently Supported Architectures
+
+Currently, `llvm-exegesis` supports the following architectures:
+
+* x86
+  * 64-bit only due to this being the only implemented calling convention
+    in `llvm-exegesis` currently.
+* ARM
+  * AArch64 only
+* MIPS
+* PowerPC
+
+Note that not all functionality is guaranteed to work on all architectures.